Accelerated Reinforcement Learning for Sentence Generation by Vocabulary Prediction.
Kazuma HashimotoYoshimasa TsuruokaPublished in: NAACL-HLT (1) (2019)
Keyphrases
- reinforcement learning
- prediction accuracy
- natural language
- text generation
- prediction algorithm
- function approximation
- generation method
- prediction model
- neural network
- optimal policy
- learning process
- genetic algorithm
- markov decision processes
- learning algorithm
- optimal control
- model free
- reinforcement learning algorithms
- machine learning
- linguistic features
- data sets